Two General Claude Code skills, side by side. Pick the right skill for your workflow with a side-by-side look at metadata, sample code, and install commands.
| Name | llm-router | unikit-verify |
|---|---|---|
| Description | Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements. Routes cheap tasks to Haiku/GPT-4o-mini and complex tasks to Sonnet/Opus/o1. Use when deciding… | Verify completed implementation against the feature plan from .unikit/plans/. Checks that all tasks were fully implemented, nothing was forgotten, code compiles, tests pass, and {{engine_name}}-specific conventions are… |
| Category | General | General |
| Sub-category | ai-tooling | general-misc |
| Tags | ai:llm | type:review |
| Author | curiositech | NintendaDev |
| License | — | MIT |
| Install | /add-skill llm-router | /add-skill unikit-verify |
flowchart TD
A{Task type?} -->|Classify / validate / format / extract| T1["Tier 1: Haiku, GPT-4o-mini (~$0.001)"]
A -->|Write / implement / review / synthesize| T2["Tier 2: Sonnet, GPT-4o (~$0.01)"]
A -->|Reason / architect / judge / decompose| T3["Tier 3: Opus, o1 (~$0.10)"]
T1 --> Q1{Quality sufficient?}
Q1 -->|Yes| Done1[Use cheap model]
Q1 -->|No| T2
T2 --> Q2{Quality sufficient?}
Q2 -->|Yes| Done2[Use balanced model]
Q2 -->|No| T3
Agent(
subagent_type: "general-purpose",
prompt: "/unikit-devcontext <fix details>",
description: "Apply fix",
skills: ["unikit-devcontext"]
)
```
Fallback: if the `Agent` tool is unavailable, invoke `/unikit-devcontext` inline.
- **`rules-agent`** — capture a new project rule spotted during verification. Expands to:
```
Agent(
…
llm-router — Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements. Routes cheap tasks to Haiku/GPT-4o-mini and complex tasks to Sonnet/Opus/o1. Use when deciding…
unikit-verify — Verify completed implementation against the feature plan from .unikit/plans/. Checks that all tasks were fully implemented, nothing was forgotten, code compiles, tests pass, and {{engine_name}}-specific conventions are…
Both are free to install. If you're unsure, install both — Claude Code skills are isolated by filename and only collide if their trigger phrases overlap (rare). The richest signal is the SKILL.md body itself — open both skill pages and read the first paragraph of each.
See all Claude Code skill comparisons · Browse all General skills · Top 100
SKILL.md files, not affiliated with, endorsed by, or sponsored by Anthropic.